Recurrent Neural Networks

Also known as RNN

Overview

Recurrent neural networks study how a model can process ordered inputs by repeatedly updating an internal state, which is useful for streaming data, long-term memory, and decisions under partial observability. Common approaches include gated LSTMs and GRUs, linear and state-space recurrences, continuous-time and spiking networks, and weight-shared loops for iterative reasoning; training ranges from backpropagation through time to online learning and parallel scans. Researchers test these models on state-tracking and recall tasks, language modeling, time-series forecasting, control, and physical-system prediction. A central tension is how to preserve useful information and stable learning over long sequences while keeping computation efficient and matching the accuracy and flexibility of Transformers.

Latest papers

329 papers24 papers in the last four weeks, down 59% on the four weeks before. 0.2% of all new papers.

Oct 16, 2026

RTSM: Adapting Recursive Models to Multivariate Time-Series Classification

Accurate multivariate time-series classification requires extracting temporal features and integrating information across a sequence. Weight-tied refinement offers a way to repeatedly process these features without allocating new parameters at each stage. Applying this principle to time series requires choosing both a temporal representation and a latent-state organization suited to classification. We introduce the Recursive Time-Series Model (RTSM), which combines a learned convolutional temporal tokenizer, single-state weight-tied refinement, and a pooled classification readout. Across all 30 UEA datasets, RTSM achieves 72.81% mean accuracy under validation-based configuration and checkpoint selection, the highest observed mean among the 17 evaluated deep-learning models and 1.60 percentage points above MambaSL. Ablations on eight datasets favor the proposed tokenizer over a simple convolutional embedding and the single-state model over the tested two-state variants. The complete classifier reaches 86.10% mean accuracy versus 84.79% for a separately trained tokenizer-only classifier. These findings identify temporal encoding and state organization as key design choices for adapting recursive architectures to time series. The resulting classifier combines competitive accuracy with a shared refinement module whose parameter count is independent of computational depth.
Oct 16, 2026

BRICE: Brain-inspired Recurrent Illusory Contour Encoder for Point Cloud Completion

Mainstream point cloud completion methods are unanimously based on deep learning architectures. On one hand, these methods tend to repetitively stacking attention modules to enhance network performance, which drifts away from the neat design of unified and interpret-able networks; on the other hand, nearly all existing architectures rely solely on feed-forward connections to propagate information, neglecting feedback from deeper layers. The recurrent neural architecture, formed by feedforward-feedback loops, have shown its ability to generate Illusory Contours (ICs) in the V1 brain region of mammals; and ICs are essentially a completion mechanism of the brain for visual information. Motivated by this, we design a Brain-inspired Recurrent Illusory Contour Encoder (BRICE) to "imagine" what is missing in the incomplete 3D point clouds. Building upon the foundation model of Predictive Coding (PC), the plug-and-play nature enables BRICE to be seamlessly integrated into mainstream point cloud completion baselines. Experimental results show that BRICE can enhance various completion baselines on different 3D datasets such as MVP2K, PCN, and PlantPCom. Our code: Https://github.com/wangyunlei-wyl/BRICE.
Oct 13, 2026

Exploring Interpretability in Deep Learning-Based Forest Classification - Separating Similar Forest Classes using Sentinel-2 Time Series

The ecological insurance theory posits that diverse forests are more resilient and better able to adapt to changing environmental conditions. Increasing drought and heat stress in Central Europe promotes mixed forests for maintaining ecosystem services. However, a diverse species distribution complicates remote sensing-based species mapping, as distinguishing pure from mixed species compositions at the pixel level remains challenging. We evaluated the potential of recurrent neural networks (RNNs) for tree-species classification from Sentinel-2 time series and investigated the spectral-temporal features underlying class discrimination, with particular emphasis on separating pure from mixed Norway spruce pixels. We compared RNN classification models with Random Forest (RF) and Extreme Gradient Boosting (XGBoost) and used Integrated Gradients (IG) to quantify feature attributions across spectral bands and time. The best-performing RNN achieved a Macro-F1 score of 0.851 on the test data, outperforming XGBoost by 0.012 and Random Forest by 0.103. Beyond classification performance, the attribution analysis revealed distinct spectral-temporal patterns associated with the separation of pure and mixed Norway spruce pixels. Attribution values increased particularly after approximately day of year (DOY) 125, while B11 showed the strongest contribution during periods of increasing spectral divergence between the two classes. These findings show that recurrent models can provide competitive classification performance while also revealing the phenological periods and spectral regions that are most relevant for distinguishing closely related forest compositions. Combining time-series classification with explainability therefore provides additional insight into the spectral-temporal mechanisms underlying tree-species discrimination and may support more detailed mapping of mixed forest structures.
Oct 13, 2026

Riding the Fixed-Point Curve: Image Classification in the Continuous Thought Machine

The Continuous Thought Machine (CTM) is a recurrent network that attends to inputs and makes predictions based on the synchronization between its neurons. On tasks spanning many domains, it displays emergent thought processes that have not been explained. We report a number of findings about how the CTM classifies images, focusing on ImageNet. Thinking steps are attracting but strongly non-normal maps exhibiting balanced amplification (Murphy and Miller, 2009); while attraction is already present at CTM initialization, training highly promotes non-normality. By Banach's theorem, the neural state thus has a locally unique attracting fixed point, which moves at every step, and the thought trajectory is the curve these fixed points trace, followed one tick behind. Most of that curve's motion is shared across images, and visible as a previously reported traveling wave of activity across neurons. The attention schedule along the thought is largely generic: shuffling queries across images at every tick costs only 7 percent of classification accuracy, while image-independent increments predict the next query with R^2 = 0.98 (held out). Our results suggest that the CTM has found a single strategy to process all ImageNet images.
Oct 13, 2026

ST-GRU PredRNN-V2: A GRU-Based Reformulation of PredRNN-V2 for Video Prediction

Video prediction requires models to capture complex spatiotemporal dependencies and to retain relevant information over long sequences. PredRNN and its successor PredRNN-V2 address this challenge with spatiotemporal Long Short-Term Memory (ST-LSTM) units that maintain two separate memory states, at the cost of a relatively complex recurrent building block. In this work, we investigate whether the simpler gating of Gated Recurrent Units (GRUs) can be transferred to spatiotemporal predictive learning. To this end, we develop a spatiotemporal GRU (ST-GRU) unit as a GRU-based alternative to the ST-LSTM. The ST-GRU replaces the ST-LSTM's three gates per memory state with two GRU-style gates (update and reset), and merges the temporal memory state into the hidden state, which reduces the number of parameters by about 5%. We incorporate the ST-GRU into PredRNN-V2 and evaluate the resulting model on the Moving MNIST video prediction benchmark, following the original experimental protocol. Averaged over ten predicted frames, the ST-GRU-based PredRNN-V2 achieves an MSE of 55.1, an SSIM of 0.883, an LPIPS of 0.065 and a PSNR of 19.53dB. It does not surpass the original ST-LSTM-based PredRNN-V2 on MSE, SSIM or PSNR, but it achieves a lower LPIPS and performs on par with the earlier ST-LSTM-based PredRNN, while using a simpler recurrent cell. These results suggest that ST-GRUs are a promising building block for spatiotemporal predictive learning and motivate further work on their design and integration.
Oct 12, 2026

Compression Through Time: An Interplay of Separability, Stationarity and Capacity

Information-theoretic and geometric compression have been widely studied as possible explanations for generalization. Yet their temporal dynamics in recurrent networks remain largely unexplored. Using discretized LSTMs, whose finite embedding space enables direct estimates of information quantities, we observe pronounced compression across the final timesteps of many datasets. We explain this effect through three competing mechanisms: (i) class separability permits stronger compression at the final timestep; (ii) shared recurrent dynamics propagate this pressure across timesteps with similar activation states, making its extent depend on temporal stationarity; and (iii) limited representational capacity opposes prolonged compression because it restricts information available for subsequent computation. We systematically test these mechanisms through controlled synthetic interventions and real-world sequence tasks. Our results identify class separability, temporal stationarity, and network capacity as key determinants of temporal compression, and suggest that compression acts as a regularizer-potentially beneficial when excess capacity is available, but harmful to generalization when it consumes memory needed for the task.
Oct 12, 2026

DeepThink: A Conceptual Model for Knowledge-Addressable Recurrent Language Modeling

This manuscript presents DeepThink, a knowledge-addressable framework for recurrent language modeling. A Knowledge Bank stores typed Knowledge Units, a Knowledge Activator selects units from the current execution state, Knowledge Assembly produces an executable configuration, and a Shared Thinking Operator updates that state. An output stage then organizes generation. This organization exposes knowledge capacity, activation width, and recurrent depth as separate design variables, supporting both complete parameter packages and fine-grained expert or low-rank modules. We formalize the interfaces and their execution semantics, including state-dependent selection, parameter-space assembly, and thinking followed by generation. For compatible templates and complete runtime-state configurations, we establish an exact Fixed-Schedule Realization of an existing fixed-depth model. Exact shared-base reparameterization and pretrained output-tail reuse provide complementary initialization constructions. Together, these results define a route from pretrained models to dynamically selected and assembled recurrent computation. A synthesis of conditional computation, recurrent models, modular parameters, and knowledge interfaces positions DeepThink within the research landscape and identifies the design questions arising from their integration.
Oct 12, 2026

Interactive 4D Volumetric Liquid Forecasting under Moving-Solid Interaction

We propose the task of Interactive 4D Volumetric Liquid Forecasting: predicting the spatiotemporal evolution of a future dense 3D liquid velocity field conditioned on how a solid object moves through it. This task provides an upstream physical forecasting primitive for systems that need to reason about motion-conditioned liquid response, including robotic liquid manipulation, digital twins, and rigid-fluid video generation. Existing works have made efforts in predicting flow around static or prescribed solid geometries and synthesizing visually plausible fluid motion. Yet these approaches provide limited coverage for interactive liquid dynamics, as they are not capable of forecasting how a moving solid induces a future full-domain liquid response. In this forecasting scenario, the hydrodynamic effect is condensed near an evolving liquid-solid interface, but the prediction target is a global spatiotemporal rollout. To address this challenge, we propose a two-level recurrent forecasting framework, TIDE/TIDES: TIDE isolates localized interface-driven forecasting, while TIDES adds transport-aware coupling and explicit stabilization to reduce accumulated rollout error. Across adapted neighboring baselines, controlled component ablations, motion/size OOD tests, and long-horizon evaluation, TIDES achieves the best forecasting performance and the ablations identify localized interaction, transport coupling, and stabilization as the key contributors. Together, our task formulation, benchmark, and TIDE/TIDES study establish a controlled foundation for moving-solid-conditioned dense liquid forecasting. The code is publicly available at https://github.com/jongwonryu/TIDE-TIDES.
Oct 10, 2026

Knowledge transfer between simple discrete worlds

Adapting to a new world and reasoning correctly about which outcomes are possible under rules one has not met before is a basic capacity underlying general intelligence. We study it in small discrete worlds: sets of grid configurations consistent with a shared set of rules, concretely Sudoku-like puzzles built from a common base and a handful of extra rules. We train a single depth-recurrent model on many combinations of rules and test it at four levels of novelty: a new puzzle, a new combination of known rules, a pairing of rules never seen together, and a rule instance not seen at all during training. The model receives the active rules either as a symbolic description or as two solved examples, and a model that gets no rule information is used as a baseline. At recombining rules it was trained on, the description matches or exceeds examples (99%99\% against 95%95\% on new combinations). On rule instances whose components never co-occurred in training, the description falls below the no-information baseline while examples stay above it. The framework allows us to test many such generalization regimes in more systematic way than benchmarks such as ARC-AGI and provides new ground for evaluating depth-recurrent reasoning models, which are typically tested on saturated Sudoku benchmarks.
Oct 10, 2026

Fitting Every Hint Is Not Enough: Premature Floods in Recurrent Algorithmic Reasoners

Recurrent algorithmic reasoners are trained with per-step hints on small graphs and run for many more steps on large ones. On breadth-first search in SALSA-CLRS, we find that a reasoner can reproduce every training hint and still fail on deep graphs: after some exact steps, it declares nodes reached before the search gets there. We call this a premature flood and trace two routes to it. In our GRU processor with a degree input, the flood is carried in the hidden state and set off when that input is in the tail of the training distribution. Setting the input higher at inference brings the flood sooner, and none of the six flooding models counts steps. Without the input, summing the neighbors' states instead of averaging them also breaks the processor. In the benchmark's own GIN and PGN, trained with its code, some seeds instead flood from a fixed step, on sparse and dense graphs alike. Clamping the degree input or adding 200 dense training graphs removes every failure of the GRU processor. Detaching the state between steps avoids the flood in that processor (0 of 23 seeds, against 6 under full backpropagation) but not with sums or a residual update, and two published remedies leave floods. None of the benchmark's test sets is both deep and dense, but its deepest one shows the second route: on its Delaunay graphs at 1,600 nodes, one GIN seed floods from step 18. We therefore recommend auditing the range of every input and aggregate, which catches the first route, and testing on deep graphs, which catches both.
Oct 9, 2026

Manifold Navigation Learning Using Recurrent Networks: Efficient Training Techniques

Position tracking is a well-studied problem in Euclidean navigation, yet comparatively little attention has been given to navigation on general manifolds, where motion is governed by the underlying geometry of the space. In this work, we formalize the problem of manifold navigation as a velocity-driven tracking task and propose a coordinate-chart-based learning framework in which learning models operate entirely in a Euclidean representation. Predicted trajectories are mapped to the manifold via an immersion function prior to error computation, allowing geometric consistency to be evaluated without explicitly enforcing manifold constraints during learning. Within this framework, we focus on Gated Recurrent Units (GRUs) for sequential position prediction on curved manifolds after comparisons with alternative recurrent architectures. We evaluate our GRU models, trained with pertinent custom loss functions, against both a standard MSE loss function and a naive vector-addition baseline. We evaluate our approach on both analytically (and numerically) defined manifolds, as well as a surface reconstructed from a LiDAR point cloud. Our results show that recurrent models can learn to approximate manifold-constrained dynamics from velocity sequences and consistently outperform Euclidean baselines. Our results demonstrate that certain custom loss functions significantly improve long-horizon prediction accuracy compared to conventional point-wise loss functions.
Oct 9, 2026

The RNN Homunculus: Learning to Gate Long-Term Memory

Learning long-range dependencies with recurrent neural networks (RNNs) is difficult because of the vanishing gradient problem. Gated recurrent neural networks like GRUs and LSTMs address this problem and are commonly explained by their ability to create additive copy paths through time. This explanation is correct, but incomplete: useful RNN gate values must themselves be learned, which is typically done with another RNN. We study this gate-learning problem through carefully controlled sequence classification tasks. Our analysis shows that gated architectures struggle when all training samples require long-range memory and thus equally suffer from the vanishing gradient problem. We intervene by adding short-dependency samples which let gated models learn solutions that capture long-dependency samples, but also generalize across different class labels. When properly learned, gated RNNs match or even exceed the test accuracy of modern architectures like Mamba and xLSTM. Overall, our results highlight gate learning as a central part of learning long-range memory and show how training data can support this process by exposing the same task over shorter dependencies.
Oct 9, 2026

Does Learning Recurrent Networks Matter in Partially Observable RL?

Reinforcement learning (RL) under partial observability typically re- lies on recurrent networks to encode temporal information, with the recurrent module trained jointly with the policy or value function. This raises a natural question: is learning the recurrent network actually necessary? In this paper, we investigate whether a frozen recurrent network can provide sufficient memory for solving par- tially observable Markov decision processes (POMDPs). Motivated by the theoretical foundations of Reservoir Computing (RC) and Generalized Reservoir Computing (GRC), we study a simple archi- tecture that combines a fixed recurrent network with a trainable nonlinear output module. We evaluate this approach across tasks with varying memory demands, observation modalities, and action spaces. Surprisingly, frozen recurrent networks support recall over hundreds of steps and achieve competitive control performance across diverse POMDPs, while using less than half the number of trainable parameters required by their fully trainable counterparts. These results suggest that learning the recurrent memory module is not always necessary for solving POMDPs. Frozen recurrent networks therefore provide a simple, parameter-efficient, and sur- prisingly strong baseline for partially observable RL. Our source code is available at https://github.com/Aphlios/FRN-POMDP
Oct 8, 2026

Neural Networks for Temporal Pattern Recognition and Dynamic Arm Gesture Speed Estimation for Robot Control

Deploying intelligent robotic systems that interact with humans through gestures requires neural networks capable of recognizing diverse temporal patterns. We present a systematic benchmark of ten abstract sequential tasks--five permutation-invariant (set) and five order-dependent (sequence) problems--evaluated across eighteen neural network architectures spanning recurrent, convolutional, attention-based, and set-function families. Beyond the core architecture-task grid, we explore numerous preprocessing and target-variable transformations, yielding more than 250 distinct experimental configurations. All variants are trained and tested under strictly identical conditions (fixed random seeds, shared hyperparameters, shared data splits) to ensure fair and reproducible comparison. Ranking across all ten tasks reveals four consistently top-performing architectures--BiGRU, TCN, Conv1D, and GRUReLU--all compact enough for real-time deployment (under 2,000 parameters in the benchmark setting). Based on this ranking, we apply three architecturally diverse top models (BiGRU, TCN, and GRUReLU) to a practical robotics problem: estimating the execution speed of dynamic arm gestures from skeletal keypoint sequences. Three speed interpretations (peak count, period time, and mean spike spacing) are evaluated on a custom dataset of eight traffic-related gesture classes comprising 256,710 frames recorded via OpenPose. The best configuration achieves a mean absolute error of 0.198 on the peak-count interpretation, corresponding to roughly 5% relative error, while the period-time interpretation reaches approximately 4% relative error, and the mean spike spacing interpretation approximately 8% relative error. These results demonstrate that neural networks can reliably estimate gesture speed from skeletal data, opening a path toward speed-aware gesture-controlled robotic systems.
Oct 7, 2026

Reconstruction of Multiscale Plasma Dynamics Across Operating Regimes

Reconstructing spatially resolved plasma dynamics from few sensors is essential for diagnostics, reduced-order modelling and control, yet remains difficult because the sparse measurements incompletely constrain multiscale, regime-dependent degrees of freedom. The Shallow Recurrent Decoder (SHRED) partially addresses spatial sparsity by using measurement histories; however, its fully connected decoder provides no explicit mechanism for resolving spatial structure across scales or explicit parametric dependency. We introduce the Recurrent Multiscale Affine-modulated Inference Network (ReMAIN), which preserves SHRED's recurrent temporal encoding but replaces its decoder with a U-Net whose feature hierarchy is conditioned by the recurrent state through feature-wise linear modulation. The temporal representation supplies both a dense prior and scale-specific modulation throughout the U-Net. A parametric extension jointly embeds the operating condition and sensor history, enabling reconstruction to adapt as the governing dynamics change with operating regime. ReMAIN is first benchmarked against SHRED on six one-dimensional nonlinear PDEs representing diverse dynamics. Across all benchmarks, it reduces reconstruction errors on unseen trajectories and more faithfully resolves sharp transitions, localized extrema and fine-scale variations. The parameter-conditioned model is then demonstrated on a collisionless E×BE \times B plasma subject to perpendicular axial electric and radial magnetic fields, with the electric-field strength serving as the operating parameter. ReMAIN reconstructs the high-dimensional, multiscale plasma state and recovers its regime-dependent spatiotemporal dynamics at electric-field strengths withheld from training. Together, ReMAIN improves sparse-sensor full-state reconstruction and, through parameter conditioning, generalizes across plasma operating regimes.
Oct 7, 2026

Learning infinite context windows in recurrent architectures via spatial neural computing

Recurrent neural networks (RNNs) offer linear-time scaling with sequence length while requiring only constant memory, yet they struggle to capture long-range dependencies due to vanishing gradients and limited receptive fields. To address these limitations, we introduce a second-order recurrent model in which the standard neuron-to-neuron communication is replaced by a spatially evolving field governed by (discretized) partial differential equations. Drawing inspiration from the role of cortical waves in brain computation, this mechanism allows structured spatiotemporal patterns to serve as an implicit, high-capacity memory. We show that the resulting model is equivalent to a structured infinite-order RNN in which the current state depends explicitly on its entire history of past states, yielding an effectively unbounded receptive field with a fixed number of parameters. We further derive constructive conditions to ensure marginal stability, constraining the gradient spectrum on the unit circle and thereby eliminating vanishing and exploding gradients. Empirically, the proposed architecture outperforms other recurrent models on long-horizon benchmarks while using substantially fewer parameters, demonstrating that spatial dynamics can effectively bridge the gap between efficient inference and long-term memory.
Oct 6, 2026

Continuous Memory Machines

Recurrent neural networks typically compress information into a single vector-valued recurrent state, forcing short-term computation and long-term retention to share the same representation. Past extensions alleviate this bottleneck by increasing the memory capacity or separating timescales, but lack the combination of rapid neuron-level processing and longer-term retention found in biology. To that end, we introduce the Continuous Memory Machine (CMM), a recurrent architecture with matrix-valued short- and long-term memory states serving distinct functional roles. Building on the Continuous Thought Machine (CTM), the CMM's short-term memory tracks recent neural activity, with uniquely parameterized neuron-level models learning to use these activity patterns for computation. A persistent long-term memory stores information for later use, with a Transformer jointly updating both memory stores, providing an expressive bidirectional read--write mechanism such that each store can reorganize its own contents and both read from and write to the other. Across algorithmic, in-context learning, and recurrent reasoning tasks, the CMM outperforms a broad suite of baselines, exhibiting stronger generalization than prior memory-augmented networks while preserving the CTM's interpretable attention patterns. Code is available at https://github.com/SakanaAI/continuous-memory-machines.
Oct 6, 2026

Forecast Accuracy Is Not Trading Profit: Evolving Small Recurrent Networks for Stock Return Prediction

Time series forecasting models are typically compared on pointwise error, which scores a prediction in isolation from the decision it is produced for, and a lower forecast error does not imply a better decision downstream. A parallel debate asks whether modern transformer architectures forecast better than recurrent and other lightweight models. We compare linear, fixed recurrent, transformer, and mixing based architectures against recurrent networks evolved by neuroevolutionary architecture search, evaluating each on forecast accuracy and on the net return of a daily long/short strategy. All models are fit on a pooled panel, one network trained across the whole universe. Across four mid-cap portfolios and three trading years, the evolved networks rank first on both forecast accuracy and net trading performance, while the second most accurate model loses money once positions are formed and costs are charged. The advantage tracks a horizon match, since rank IC for the evolved networks rises from a one-day to a ten-day scoring horizon while every model above 300 parameters declines. They are also the cheapest end to end: a CPU-only search of 16 minutes yields 66-weight networks that predict in 10.8~μμs on a Raspberry Pi Zero, against transformer baselines of up to 817,153 parameters that require GPU training.
Oct 6, 2026

Learned Monotone Recurrent Features in Governed Credit Scoring: The Price of the Frame and the Necessity of Macro Conditioning

Regulated credit scoring requires scores monotone non-decreasing in every exposure input. Deployed pipelines -- hand-crafted monotone aggregates feeding sign-constrained gradient boosting -- already meet this by composition; the open question is what learned temporal aggregation is worth inside one. We answer on five production-scale credit datasets at matched admissibility (one priced baseline convention excepted), with a monotone recurrent architecture whose per-input guarantee we extend, with proofs, to vector-valued inputs and to exogenously macro-conditioned decay gates, severities, thresholds, and peak memory. Two findings result. First, a strictness ladder: the value of learned monotone features rises with governance-frame strictness -- zero on unconstrained engineered panels, maximal in summaries-only frames -- replicated across two datasets and an official temporal-stability metric, though unconditioned features degrade on externally adjudicated later weeks. Second, a conditioning-delivery asymmetry under regime shift. On a train-on-boom, test-on-crisis mortgage design, two public macroeconomic series hurt as input columns, yet conditioning the recurrence on them delivers the paper's only learned-block crisis-cohort uplifts. The confirmed effect: +0.006 to +0.013 AUC on an internally pre-registered Freddie Mac replication, at all five held-out seeds. The discovery estimate: +0.015 to +0.021 on Fannie Mae (three of five seeds post hoc), worth 10-27 basis points of defaulted balance at an 80% approval cutoff, and grows with early-prepaid loans excluded. A state-level test identifies the mechanism: between-cohort calibration transfer. A pandemic-band episode bounds scope: under forbearance-distorted labels the gain generalizes at a quarter to a third of crisis size on Fannie Mae, on Freddie Mac only against the capacity control.
Oct 3, 2026

Learning to Remember: Distilling Memory Retention for Compact Recurrent Neural Networks

Deep learning models, particularly recurrent neural networks and their variants, such as long short-term memory, have significantly advanced time series analysis. These models capture complex, sequential patterns in time series, enabling real-time assessments. However, their high computational complexity and large model sizes pose challenges for deployment in resource-constrained environments, such as wearable devices and edge computing platforms. Knowledge Distillation (KD) offers a solution by transferring knowledge from a large, complex model (teacher) to a smaller, more efficient model (student), thereby retaining high performance while reducing computational demands. Current KD methods, originally designed for computer vision tasks, neglect the unique temporal dependencies and memory retention characteristics of time series models. To bridge this gap, we propose a novel KD framework termed Memory-Discrepancy Knowledge Distillation (MemKD). MemKD leverages a specialized loss function to capture memory retention discrepancies between the teacher and student models across subsequences within time series data, ensuring that the student model effectively mimics the teacher's behaviour. This approach facilitates the development of compact, high-performing recurrent neural networks suitable for real-time, time series analysis tasks. We provide additional experiments, in-depth theoretical analysis, and insights into the proposed framework across extended time series benchmarks. Our experiments demonstrate that MemKD significantly outperforms state-of-the-art KD methods. Additionally, we demonstrate that it can match the teacher model's performance across a wide range of compression levels, achieving notable reductions in parameter count and memory usage without a significant loss in accuracy.
Oct 2, 2026

On architectural choices for interpretability and thermodynamic consistency in Physically Recurrent Neural Networks in the low-data regime

In this paper, we unravel the effect of different decoder architectures on the interpretability of the latent space of the Physically Recurrent Neural Network. Particular emphasis is given to a new weight normalization constraint, which acts as a regularization technique and enables robust training in the low-data regime. A brief visual exploration illustrates how these changes impact the latent space and how the fictitious stress can align with the true state of the RVE without explicit training. Reaping the benefits of a meaningful latent space, a case study illustrates how information from the microscopic level can be retrieved and incorporated into a multi-task approach that does not require extra parameters or larger training sets. Another key contribution shows that a specific architectural choice can naturally lead to a thermodynamically consistent formulation. By enforcing an adjoint encoder-decoder structure with positive scalar contributions, this modification ensures energy consistency across scales and non-negative dissipation, leading to even lower training requirements. This alternative completes the study on interpretability, inductive bias, and thermodynamic consistency, and demonstrates that data efficiency can be improved with careful architectural choices rooted in the underlying physics.
Oct 2, 2026

Most-Recent Anchoring with Recurrent Ordering for Time Series Forecasting

Long-term forecasting models commonly process all patches in a look-back window using the same fixed stack. Older contextual patches and recent evidence therefore receive the same computational depth. Yet the information closest to the forecast and the more distant context do not contribute equally. Uniform processing leaves this distinction unexpressed in the architecture. We propose MARO, a Most-Recent Anchoring with Recurrent Ordering model that processes the look-back window from the most recent patch to the oldest. The most recent patch serves as the anchor. It initializes the latent state and conditions each subsequent step, so older patches are folded into a representation that remains centered on recent evidence. A single shared module is reused at every step, so extending the scan further into the past introduces no additional parameters. Intermediate states retained during the scan allow the forecast head to weigh short and long portions of the history separately. This expresses recency through the order of recurrent refinement. Extensive experiments across multiple real-world time series datasets show that MARO achieves state-of-the-art performance on both long-term and short-term forecasting tasks.Ablation studies examine the contribution of the main architectural components.
Oct 2, 2026

Self-Repairing Recurrent Ensembles for Real-Time Recovery from Distribution Shift

Deploying a pretrained controller exposes it to conditions that are absent from its training data. Sensor drift, outright sensor failure and accumulating measurement noise all induce a distribution shift that can collapse an otherwise competent policy; typically at a point in time where no expert is available to supply corrective labels. We present a method that lets a policy recover from such shifts online and without supervision. Our controller is an ensemble of recurrent networks, each of which observes a randomly masked subset of the observation vector, and whose Gaussian outputs are combined through sequential Kalman fusion so that confident members dominate the consensus action. At deployment, we treat this consensus as a self-supervised label and fine-tune each member towards it, scaling each member's contribution proportional to the complement of its squared Kalman gain. Gradients are computed using RFLO, an efficient and biologically plausible approximation of Real-Time Recurrent Learning, so that a parameter update follows every environment step and the policy reacts to a shift as it unfolds. On a range of simulated continuous control tasks, our approach recovers close to the original performance after a sensor shift, while ensembles that see the full observation are unable to recover. The same framework subsumes fully online interactive imitation learning: when an expert is present, the consensus label is replaced by the expert action and the identical update rule refines the policy during teleoperation.
Oct 2, 2026

Where Does Jagged Competence Come From?

Capable systems often show jagged competence: low average error alongside failures on particular inputs. We ask where it comes from in a task built from two known layers. A lower layer A computes five per-slot sums from records; an upper layer B uses the slot-1 sum and a mode carried over from earlier boards to predict the next board's category, so B cannot be computed from the current A alone: B is a strict extension of A. We train small recurrent networks on B and measure, against exact ground truth, what they acquire of A. The central finding is that learning B gives the network a jagged version of A, measured through probe readability and supervised outputs. It is readable where B needs it (slot 1, 97-98% by a linear probe) and becomes less readable where B does not (the other slots, 5-10%); category misreads concentrate near the slot-1 cutoffs; and when A is trained explicitly it comes out only approximately right. The networks show jagged competence in B: natural KL below 3×10−43\times10^{-4} bits coexists with a maximum law TV of about 0.25 on constructed histories. Matched experiments show that even a good A is not enough: connecting a learned A to B cuts misreads 1.3 to 17-fold, the same exact A gives fewer misreads as one-hot inputs (0-2) than as numerical inputs (10-317), one B update makes an exact A inexact unless the B gradient is blocked, and exact A still leaves some B failures. In this task, uneven acquisition, access and preservation of the lower theory explain part of the jagged competence of a network that learns the theory built on it; some failures remain unexplained. Whether the same holds in larger systems is a test to run.
Oct 2, 2026

RAOA: Alternating-Operator Neural Computation with Programmable Radio Propagation

Can programmable radio propagation serve as computational depth rather than only as a communication channel or one-shot analog transform? We introduce the Radio Alternating Operator Ansatz (RAOA), a recurrent computing architecture that alternates an energy-derived problem update with a mixing update over a persistent latent state. Recomputing the problem field after each mix makes repeated passes compositional even when the same learned controls are reused across depth. We evaluate this idea through exact discrete optimization, constrained programmable-propagation simulation, and pretrained-model adaptation. On discrete objectives, repeated execution can improve solution quality without increasing the learned-control count, and the same formulation handles higher-order interactions directly. A passive phase-only free-space model further shows that the required operators can be approximated by programmable propagation while retaining useful downstream behavior despite realization error. When inserted as a zero-initialized residual adapter, RAOA adapts pretrained language models with WikiText performance close to a matched shallow MLP across three model families, while reasoning-task transfer remains model-dependent. Together, these results connect alternating-operator computation, programmable radio propagation, and neural adaptation within one recurrent framework. The RF realization evidence is simulation-based rather than a hardware demonstration.
Oct 1, 2026

A foundation for systematic analysis of transformers and RNNs for tractography

Machine learning (ML) has emerged as a promising approach for improving diffusion MRI (dMRI) tractography, a task that remains limited by the intrinsic tension between local diffusion information and global anatomical plausibility. In this work, we systematically evaluate recurrent neural networks (RNNs) and Transformer models for iterative tractography, with particular attention to training strategies, input representations (including convolutional neural network (CNN)-based embeddings and end-of-sequence (EOS) tokens), and hyperparameter selection. We introduce a generation-validation phase enabling supervision at the streamline level during training, allowing supervision despite the mismatch between local loss functions and global streamline quality. Using the ISMRM2015 tractography challenge dataset, our models achieve the highest reported performance to date. Through controlled experiments, we quantify the impact of missing bundles, noisy or imperfect training streamlines, and invalid fibers in the training set. Finally, we demonstrate the applicability of our best-performing models for in vivo data from the Tractoinferno database. Overall, our results highlight both the potential and the limits of sequence-based deep learning models such as Transformers and RNNs for tractography, and emphasize the need for improved phantoms and evaluation methods for in vivo validation. We provide takeaways and recommendations for future researchers training and validating sequence-based supervised methods for tractography.
Oct 1, 2026

From Redundancy to Minimality: Fixed-Point-Guided Hierarchical Reduction of Learned Piecewise-Linear Dynamics

Understanding a nonlinear dynamical system from time series requires not only reproducing its trajectories, but also identifying a simple representation that preserves its essential dynamical structure. Almost-linear recurrent neural networks (AL-RNNs) are piecewise-linear RNNs in which only a subset of units use ReLU nonlinearities, so that nonlinear capacity is explicitly controlled by the number of ReLU units. Their activation patterns define linear regions, represented as symbols, whose observed transitions form a symbolic transition graph. However, directly training AL-RNNs with few ReLU units to realize minimal dynamical representations can be unreliable. We ask whether an AL-RNN with more ReLU units can instead be trained first and systematically reduced to a minimal dynamical representation. We introduce a fixed-point-guided hierarchical reduction procedure that progressively linearizes selected ReLU units, merging neighboring linear regions and graph nodes while preserving distinct symbols containing fixed points (FPs). The resulting reduction tree defines a hierarchy of progressively simpler candidates. Each reduced candidate is initialized from the parent parameters and retrained under guidance from the parent dynamics. We also prove that reproducing QQ distinct fixed points requires at least QQ FP-containing symbols, providing a certificate of symbol-level minimality when this bound is attained. On the 3-scroll Chua system, direct training with the theoretical minimum of three ReLU units achieves high-fidelity minimal realizations in only 20% of seeds, whereas our learn-reduce-retrain strategy increases the seed-macro success rate to approximately 71% at the same final nonlinear capacity. These results show that redundant nonlinear capacity can serve as a scaffold for discovering and realizing minimal dynamical representations.
Oct 1, 2026

Extreme Length Generalization in a Compact Recurrent Architecture for One-Shot Exploration

Autonomous robots on one-shot missions run over horizons far longer than the trajectories seen during training, under a fixed onboard compute budget. We present FRANK, a 507K-parameter recurrent architecture that combines tau-gated recurrent modules, content-addressable memory, and a feedforward reflex pathway. We evaluate it against recurrent, state-space, and reduced modular baselines at matched parameter count on four algorithmic sequence tasks, trained at length 5-20 and evaluated out to two million tokens. At 100,000x the maximum training length, 6 of 10 FRANK seeds retain exactly 100.0% accuracy, while none of the 50 baseline configurations does, five architectures at ten seeds each with none left incomplete (Fisher exact, two-sided p = 4.2E-6. Targeted lesions across the four tasks yield four distinct component-reliance profiles, consistent with task-dependent allocation across the recurrent, memory, and reflex pathways. Separately, a FRANK policy trained in simulation drives a physical ground vehicle to commanded waypoints through obstacles without teleoperation.
Sep 30, 2026

Disentangling Computation in Multi-Task Neural Networks with the Green's Operator

How is computation organized and reused across tasks and time in a trained recurrent network? Most analyses emphasize the geometry of neural activity, dynamical motifs, or local perturbation growth. We instead study the network's global first-order perturbation response. The finite-horizon Green's operator maps perturbations at each source along a trajectory to their downstream state-space responses and therefore directly represents perturbation routing. Simple reductions of this operator provide task-to-task and time-to-time views of the same computation, while matrix-free products make these views accessible without constructing the full operator. In a flexible multitask recurrent network, task reductions reveal structured reuse of known computational motifs, while temporal reductions reveal causal pathways and how they emerge during training. Our main point is simple: the Green's operator provides a global response geometry for mapping the organization of learned dynamical computation.
Sep 30, 2026

Finite-Horizon Fisher Memory in Two-Sided Power-Bounded Recurrent Systems

We analyse allocation, admission and post-write retention in finite-horizon linear-Gaussian noisy recurrent memories. At every horizon, the directional Fisher memory MnM_n satisfies tr⁡Mn=N\operatorname{tr}M_n=N: non-normality redistributes information but cannot raise its spherical average, while normal carriers satisfy Mn=IM_n=I. For bi-power-bounded carriers, we derive uniform 1/n1/n lag bounds, identify the limit of MnM_n with the inverse of the classical Cesàro asymptotic limit of W⊤W^\top, and give finite-horizon error bounds. A time-varying coupling defines an end-to-end store operator. The writer-optimal direction need not be store-optimal. After writing ends, an invertible hold preserves the full stored Fisher matrix. Additive contamination bounded by αα times the closure covariance retains at least 1/(1+α)1/(1+α) of that matrix; a covariance-aware decoder attains the corresponding accuracy. With recurrent carriers held fixed, training input masks and linear readouts approached the task-specific optimum in 160 runs, with median normalized Rayleigh efficiency above 0.9980.998. Binary accuracy matched the Gaussian prediction to mean absolute error below 0.0020.002 over more than four orders of magnitude in JJ. In a separate pre-specified study of 320 runs, trained masks followed the designated input-time objective in both carrier types, in 16 of 16 draws. These studies used development-seen carriers and are pre-specified validations, not blind holdouts. The same fixed design reproduced the objective-specific result in 16 of 16 draws on carriers unused before run commitment. Exact isolation preserved information, while a decoder fixed at its training horizon fell to chance; inverse-adjoint transport restored its sampled decisions to numerical precision.